ICDE 2026 | 【第1轮】时空数据(Spatial-Temporal)论文总结(预测,众包,空间索引等)
本文总结了ICDE 2026会议中时空数据领域的8篇研究论文。研究主题涵盖时空预测、用户轨迹链接、空间众包、空间索引等方向。其中5篇论文已公开预印本,包括基于强化学习的空间索引基准测试、分布式空间连接优化、城市时空预测的Mamba模型等创新工作。其他研究涉及高保真任务分配、大规模路网交通预测、物流轨迹预测等应用场景。这些论文展示了时空数据处理领域在算法优化、模型创新和实际应用方面的最新进展,为相关
ICDE 2026在2026年5月4日至8日在加拿大蒙特利尔(Montréal, Canada)举行。
本文总结了ICDE 2026第一轮(round 1)有关时空数据(Spatial Temporal)的Research Track相关文章,共计8篇。
时空数据Topic:时空预测,用户轨迹链接(TUL),空间众包,空间索引,空间数据管理等
| 1. Spatiotemporal Sketch Disaggregation: Streaming Analytics with Heterogeneous Resources 2. [Experiment, Analysis, and Benchmark] Benchmarking RL-Enhanced Spatial Indices Against Traditional, Advanced, and Learned Counterparts 3. SOLAR: Scalable Distributed Spatial Joins through Learning-based Optimization 4. High-Fidelity Task Assignment in Spatial Crowdsourcing via Implicit Human Feedback 5. Damba-ST: Domain-Adaptive Mamba for Efficient Urban Spatio-Temporal Prediction 6. Efficient Traffic Forecasting on Large-Scale Road Network by Regularized Adaptive Graph Convolution 7. Trajectory–User Linking via Heterogeneous Preference Graph and Dual-Encoder Mutual Distillation 8. TransLGX: A Self-contained Model to Predict the Entire Lifecycle and complete state of Logistics Package Trajectories |
|---|

1 Spatiotemporal Sketch Disaggregation: Streaming Analytics with Heterogeneous Resources
作者:Jonatan Langlet (KTH Royal Institute of Technology)*; Peiqing Chen (University of Maryland, College Park); Michael Mitzenmacher (Harvard University); Zaoxing Liu (University of Maryland, College Park); Ran Ben Basat (University College London); Gianni Antichi (Politecnico di Milano)
关键词:Sketch
2 [Experiment, Analysis, and Benchmark] Benchmarking RL-Enhanced Spatial Indices Against Traditional, Advanced, and Learned Counterparts
链接:https://www.arxiv.org/abs/2512.11161
作者:Guanli Liu (The University of Melbourne)*; Renata Borovica-Gajic (The University of Melbourne); Hai Lan (RMIT University); Zhifeng Bao (RMIT University)
关键词:空间索引,强化学习,benchmark

3 SOLAR: Scalable Distributed Spatial Joins through Learning-based Optimization
链接:https://arxiv.org/abs/2504.01292
作者:Yongyi Liu (University of California, Riverside)*; Ahmed Abdelmaguid (University of California, Riverside); Ahmed Mohamood (Google LLC); Amr Magdy (University of California, Riverside); Minyao Zhu (Google LLC)
关键词:空间连接,空间数据库

4 High-Fidelity Task Assignment in Spatial Crowdsourcing via Implicit Human Feedback
作者:Qingshun Wu (Zhengzhou University); Yafei Li (Zhengzhou University)*; Lei Gao (Zhengzhou University); Guanglei Zhu (Zhengzhou University); Lei Chen (Beijing Institute of Technology); Mingliang Xu (Zhengzhou University)
关键词:空间众包,高保真
5 Damba-ST: Domain-Adaptive Mamba for Efficient Urban Spatio-Temporal Prediction
链接:https://arxiv.org/abs/2506.18939
作者:Rui AN (The Hong Kong Polytechnic University)*; Yifeng Zhang ( The Hong Kong Polytechnic University); Ziran Liang (The Hong Kong Polytechnic University); Wenqi Fan (The Hong Kong Polytechnic University); Yuxuan Liang (The Hong Kong University of Science and Technology (Guangzhou)); Xuequn Shang (Northwestern Polytechnical University); Qing Li (The Hong Kong Polytechnic University)
关键词:时空预测,mamba,域适应

6 Efficient Traffic Forecasting on Large-Scale Road Network by Regularized Adaptive Graph Convolution
作者:Kaiqi Wu (Sun Yat-Sen University); Weiyang Kong (Sun Yat-Sen University); Sen Zhang (Sun Yat-Sen University); Zitong Chen (Sun Yat-Sen University); Yubao Liu (Sun Yat-Sen University)*
关键词:交通预测,大规模路网,自适应图卷积
7 Trajectory–User Linking via Heterogeneous Preference Graph and Dual-Encoder Mutual Distillation
作者:ZEMING TIAN (Sun Yat-sen University); Zixin Qin (Sun Yat-sen University); Huaijie Zhu (Sun Yat-sen University)*; Ningning Cui (Chang’an University); Wei Liu (Sun Yat-sen University); Jianxing Yu (Sun Yat-sen University); Jian Yin (Sun Yat-sen University)
关键词:用户轨迹链接(TUL),相互蒸馏
8 TransLGX: A Self-contained Model to Predict the Entire Lifecycle and complete state of Logistics Package Trajectories
作者:Yichen Song (Zhejiang Universitiy); Jianfeng Zhou (Bytedance); Jian-Ya Ding (Bytedance)*; Renhao Cao (Bytedance)
关键词:预测物流包裹轨迹
更多推荐


所有评论(0)